* enc/iso_8859_5.c: Large omicron should lowercase to small omicron.

* test/ruby/test_big5.rb, test/ruby/test_cp949.rb,
  test/ruby/test_euc_jp.rb, test/ruby/test_euc_kr.rb,
  test/ruby/test_euc_tw.rb, test/ruby/test_gb18030.rb,
  test/ruby/test_gbk.rb, test/ruby/test_iso_8859.rb,
  test/ruby/test_koi8.rb, test/ruby/test_shift_jis.rb,
  test/ruby/test_windows_1251.rb: new tests for encoding.

* test/ruby/test_utf16.rb, test/ruby/test_utf32.rb,
  test/ruby/test_regexp.rb: add tests.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@16759 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 65 insertions, 0 deletions

diff --git a/test/ruby/test_utf16.rb b/test/ruby/test_utf16.rb
index d26cdc0d9a..c10463b2b3 100644
--- a/test/ruby/test_utf16.rb
+++ b/test/ruby/test_utf16.rb
@@ -290,4 +290,69 @@ EOT
     assert_equal(e, "abc".encode("utf-16be").count("^b".encode("utf-16be")))
     assert_equal(e, "abc".encode("utf-16le").count("^b".encode("utf-16le")))
   end
+
+  def test_header
+    assert_raise(ArgumentError) { eval("# encoding:utf-16le\nfoo") }
+    assert_raise(ArgumentError) { eval("# encoding:utf-16be\nfoo") }
+  end
+
+
+  def test_is_mbc_newline
+    sl = "f\0o\0o\0\n\0b\0a\0r\0\n\0b\0a\0z\0\n\0".force_encoding("utf-16le")
+    sb = "\0f\0o\0o\0\n\0b\0a\0r\0\n\0b\0a\0z\0\n".force_encoding("utf-16be")
+    al = sl.lines.to_a
+    ab = sb.lines.to_a
+    assert_equal("f\0o\0o\0\n\0".force_encoding("utf-16le"), al.shift)
+    assert_equal("b\0a\0r\0\n\0".force_encoding("utf-16le"), al.shift)
+    assert_equal("b\0a\0z\0\n\0".force_encoding("utf-16le"), al.shift)
+    assert_equal("\0f\0o\0o\0\n".force_encoding("utf-16be"), ab.shift)
+    assert_equal("\0b\0a\0r\0\n".force_encoding("utf-16be"), ab.shift)
+    assert_equal("\0b\0a\0z\0\n".force_encoding("utf-16be"), ab.shift)
+
+    sl = "f\0o\0o\0\n\0".force_encoding("utf-16le")
+    sb = "\0f\0o\0o\0\n".force_encoding("utf-16be")
+    sl2 = "f\0o\0o\0".force_encoding("utf-16le")
+    sb2 = "\0f\0o\0o".force_encoding("utf-16be")
+    assert_equal(sl2, sl.chomp)
+    assert_equal(sl2, sl.chomp.chomp)
+    assert_equal(sb2, sb.chomp)
+    assert_equal(sb2, sb.chomp.chomp)
+
+    sl = "f\0o\0o\0\n".force_encoding("utf-16le")
+    sb = "\0f\0o\0o\n".force_encoding("utf-16be")
+    assert_equal(sl, sl.chomp)
+    assert_equal(sb, sb.chomp)
+  end
+
+  def test_code_to_mbc
+    assert_equal("a\0".force_encoding("utf-16le"), "a".ord.chr("utf-16le"))
+    assert_equal("\0a".force_encoding("utf-16be"), "a".ord.chr("utf-16be"))
+  end
+
+  def utf8_to_utf16(s, e)
+    s.chars.map {|c| c.ord.chr(e) }.join
+  end
+
+  def test_mbc_case_fold
+    rl = Regexp.new(utf8_to_utf16("^(\u3042)(a)\\1\\2$", "utf-16le"), "i")
+    rb = Regexp.new(utf8_to_utf16("^(\u3042)(a)\\1\\2$", "utf-16be"), "i")
+    assert_equal(Encoding.find("utf-16le"), rl.encoding)
+    assert_equal(Encoding.find("utf-16be"), rb.encoding)
+    assert_match(rl, utf8_to_utf16("\u3042a\u3042a", "utf-16le"))
+    assert_match(rb, utf8_to_utf16("\u3042a\u3042a", "utf-16be"))
+  end
+
+  def test_surrogate_pair
+    sl = "\x42\xd8\xb7\xdf".force_encoding("utf-16le")
+    sb = "\xd8\x42\xdf\xb7".force_encoding("utf-16be")
+
+    assert_equal(1, sl.size)
+    assert_equal(1, sb.size)
+    assert_equal(0x20bb7, sl.ord)
+    assert_equal(0x20bb7, sb.ord)
+    assert_equal(sl, 0x20bb7.chr("utf-16le"))
+    assert_equal(sb, 0x20bb7.chr("utf-16be"))
+    assert_equal("", sl.chop)
+    assert_equal("", sb.chop)
+  end
 end